Browse — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "@saiden/browse",
"source": {
"kind": "package",
"origin": "@saiden/browse"
},
"server": {
"name": "@saiden/browse"
}
},
"grade": "B",
"score": {
"score": 87,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-INJ-SCHEMA-1",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"kind": "client",
"term": "verification-discount",
"level": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.13"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (40 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-010",
"title": "Dynamic evaluation of a non-literal value (dist/browser.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/browser.js:417`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/browser.js"
},
"evidence": ".page); } async eval(script) { const page = this.ensurePage(); return page.evaluate(script);",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/browser.js",
"line": 417,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"eval\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"eval\" appears to run shell commands or evaluate code (keyword \"eval\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "eval"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/browser.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/browser.js:417`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/browser.js"
},
"evidence": ".page); } async eval(script) { const page = this.ensurePage(); return page.evaluate(script);",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/browser.js",
"line": 417,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/browser.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/browser.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/browser.js"
},
"evidence": "ort { exec } from 'node:child_process'; import { resolve } from 'node:path'; import { promisify } from 'node:util'; impo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/browser.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/chrome.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/chrome.js:15`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/chrome.js"
},
"evidence": "{ execSync } from 'node:child_process'; import { createDecipheriv, pbkdf2Sync } from 'node:crypto'; import { copyFileSyn",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/chrome.js",
"line": 15,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([html, metrics]) co-exist with external-action tools ([eval, upload]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
"remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
"location": {
"kind": "flow",
"name": "html → eval"
},
"evidence": "untrusted [html, metrics] → sinks [eval, upload]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"html",
"metrics"
],
"sinks": [
"eval",
"upload"
]
}
},
{
"ruleId": "MTC-INJ-SCHEMA-1",
"title": "Description names a credential store the tool cannot reach",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"import\" describes a credential store (SSH keys, cloud credentials, a keychain or an equivalent) that nothing in its input schema can address. A tool's interface is the honest statement of what it touches; prose that reaches past it is addressed to the model, not to a reader.",
"remediation": "Remove the reference, or expose the target as an explicit, validated parameter so the client can see and consent to what the tool reads.",
"location": {
"kind": "tool",
"name": "import",
"field": "description"
},
"evidence": "Keychain",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"eval\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"eval\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "eval"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"html",
"metrics"
],
"sensitiveSource": [],
"externalSink": [
"eval",
"upload"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "launch",
"tags": [],
"reasons": {}
},
{
"tool": "goto",
"tags": [],
"reasons": {}
},
{
"tool": "back",
"tags": [],
"reasons": {}
},
{
"tool": "forward",
"tags": [],
"reasons": {}
},
{
"tool": "reload",
"tags": [],
"reasons": {}
},
{
"tool": "click",
"tags": [],
"reasons": {}
},
{
"tool": "type",
"tags": [],
"reasons": {}
},
{
"tool": "query",
"tags": [],
"reasons": {}
},
{
"tool": "url",
"tags": [],
"reasons": {}
},
{
"tool": "html",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "preview",
"tags": [],
"reasons": {}
},
{
"tool": "eval",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "console",
"tags": [],
"reasons": {}
},
{
"tool": "network",
"tags": [],
"reasons": {}
},
{
"tool": "intercept",
"tags": [],
"reasons": {}
},
{
"tool": "errors",
"tags": [],
"reasons": {}
},
{
"tool": "metrics",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "a11y",
"tags": [],
"reasons": {}
},
{
"tool": "dialog",
"tags": [],
"reasons": {}
},
{
"tool": "cookies",
"tags": [],
"reasons": {}
},
{
"tool": "storage",
"tags": [],
"reasons": {}
},
{
"tool": "hover",
"tags": [],
"reasons": {}
},
{
"tool": "select",
"tags": [],
"reasons": {}
},
{
"tool": "keys",
"tags": [],
"reasons": {}
},
{
"tool": "upload",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "scroll",
"tags": [],
"reasons": {}
},
{
"tool": "viewport",
"tags": [],
"reasons": {}
},
{
"tool": "emulate",
"tags": [],
"reasons": {}
},
{
"tool": "wait",
"tags": [],
"reasons": {}
},
{
"tool": "close",
"tags": [],
"reasons": {}
},
{
"tool": "session_save",
"tags": [],
"reasons": {}
},
{
"tool": "session_restore",
"tags": [],
"reasons": {}
},
{
"tool": "import",
"tags": [],
"reasons": {}
},
{
"tool": "favicon",
"tags": [],
"reasons": {}
},
{
"tool": "convert",
"tags": [],
"reasons": {}
},
{
"tool": "resize",
"tags": [],
"reasons": {}
},
{
"tool": "crop",
"tags": [],
"reasons": {}
},
{
"tool": "compress",
"tags": [],
"reasons": {}
},
{
"tool": "thumbnail",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "a0aa33d5c600139aac64108cec41c8a9ac135d1f61d29735069b76bf38d3d825",
"stats": {
"tools": 40,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 2,
"low": 1,
"info": 0
}
}
}